weather_df = 
  rnoaa::meteo_pull_monitors(
    c("USW00094728", "USW00022534", "USS0023B17S"),
    var = c("PRCP", "TMIN", "TMAX"), 
    date_min = "2021-01-01",
    date_max = "2022-12-31") |>
  mutate(
    name = recode(
      id, 
      USW00094728 = "CentralPark_NY", 
      USW00022534 = "Molokai_HI",
      USS0023B17S = "Waterhole_WA"),
    tmin = tmin / 10,
    tmax = tmax / 10) |>
  select(name, id, everything())
## using cached file: /Users/taa-ra/Library/Caches/org.R-project.R/R/rnoaa/noaa_ghcnd/USW00094728.dly
## date created (size, mb): 2023-10-02 22:05:34.479049 (8.525)
## file min/max dates: 1869-01-01 / 2023-09-30
## using cached file: /Users/taa-ra/Library/Caches/org.R-project.R/R/rnoaa/noaa_ghcnd/USW00022534.dly
## date created (size, mb): 2023-10-02 22:05:46.647914 (3.83)
## file min/max dates: 1949-10-01 / 2023-09-30
## using cached file: /Users/taa-ra/Library/Caches/org.R-project.R/R/rnoaa/noaa_ghcnd/USS0023B17S.dly
## date created (size, mb): 2023-10-02 22:05:50.45828 (0.994)
## file min/max dates: 1999-09-01 / 2023-09-30
weather_df
## # A tibble: 2,190 × 6
##    name           id          date        prcp  tmax  tmin
##    <chr>          <chr>       <date>     <dbl> <dbl> <dbl>
##  1 CentralPark_NY USW00094728 2021-01-01   157   4.4   0.6
##  2 CentralPark_NY USW00094728 2021-01-02    13  10.6   2.2
##  3 CentralPark_NY USW00094728 2021-01-03    56   3.3   1.1
##  4 CentralPark_NY USW00094728 2021-01-04     5   6.1   1.7
##  5 CentralPark_NY USW00094728 2021-01-05     0   5.6   2.2
##  6 CentralPark_NY USW00094728 2021-01-06     0   5     1.1
##  7 CentralPark_NY USW00094728 2021-01-07     0   5    -1  
##  8 CentralPark_NY USW00094728 2021-01-08     0   2.8  -2.7
##  9 CentralPark_NY USW00094728 2021-01-09     0   2.8  -4.3
## 10 CentralPark_NY USW00094728 2021-01-10     0   5    -1.6
## # ℹ 2,180 more rows

Basic scatterplot

ggplot(weather_df, aes(x = tmin, y = tmax)) + geom_point()
## Warning: Removed 17 rows containing missing values (`geom_point()`).

#plot of dataframe
weather_df |>
  ggplot(aes(x = tmin, y = tmax)) + 
  geom_point()
## Warning: Removed 17 rows containing missing values (`geom_point()`).

#or
ggp_weather = 
  weather_df |>
  ggplot(aes(x = tmin, y = tmax)) 

ggp_weather + geom_point()
## Warning: Removed 17 rows containing missing values (`geom_point()`).

Advanced scatterplot

ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name))
## Warning: Removed 17 rows containing missing values (`geom_point()`).

#or
ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name), alpha = .5) +
  geom_smooth(se = FALSE)
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
## Warning: Removed 17 rows containing non-finite values (`stat_smooth()`).
## Removed 17 rows containing missing values (`geom_point()`).

#seprated
ggplot(weather_df, aes(x = tmin, y = tmax, color = name)) + 
  geom_point(alpha = .5) +
  geom_smooth(se = FALSE) + 
  facet_grid(. ~ name)
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
## Warning: Removed 17 rows containing non-finite values (`stat_smooth()`).
## Removed 17 rows containing missing values (`geom_point()`).

#or
ggplot(weather_df, aes(x = date, y = tmax, color = name)) + 
  geom_point(aes(size = prcp), alpha = .5) +
  geom_smooth(se = FALSE) + 
  facet_grid(. ~ name)
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
## Warning: Removed 17 rows containing non-finite values (`stat_smooth()`).
## Warning: Removed 19 rows containing missing values (`geom_point()`).

learning assessment

weather_df |>
  filter(name == "CentralPark_NY") |>
  mutate(
    tmax_fahr = tmax * (9 / 5) + 32,
    tmin_fahr = tmin * (9 / 5) + 32) |> 
  ggplot(aes(x = tmin_fahr, y = tmax_fahr)) +
  geom_point(alpha = .5) + 
  geom_smooth(method = "lm", se = FALSE)
## `geom_smooth()` using formula = 'y ~ x'

Odds and ends

ggplot(weather_df, aes(x = date, y = tmax, color = name)) + 
  geom_smooth(se = FALSE) 
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
## Warning: Removed 17 rows containing non-finite values (`stat_smooth()`).

ggplot(weather_df, aes(x = tmax, y = tmin)) + 
  geom_hex()
## Warning: Removed 17 rows containing non-finite values (`stat_binhex()`).

Univariate plots

ggplot(weather_df, aes(x = tmax)) + 
  geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 17 rows containing non-finite values (`stat_bin()`).

#or
ggplot(weather_df, aes(x = tmax, fill = name)) + 
  geom_histogram(position = "dodge", binwidth = 2)
## Warning: Removed 17 rows containing non-finite values (`stat_bin()`).

#or
ggplot(weather_df, aes(x = tmax, fill = name)) + 
  geom_density(alpha = .4, adjust = .5, color = "blue")
## Warning: Removed 17 rows containing non-finite values (`stat_density()`).

box plots

ggplot(weather_df, aes(x = name, y = tmax)) + geom_boxplot()
## Warning: Removed 17 rows containing non-finite values (`stat_boxplot()`).

#or
ggplot(weather_df, aes(x = name, y = tmax)) + 
  geom_violin(aes(fill = name), alpha = .5) + 
  stat_summary(fun = "median", color = "blue")
## Warning: Removed 17 rows containing non-finite values (`stat_ydensity()`).
## Warning: Removed 17 rows containing non-finite values (`stat_summary()`).
## Warning: Removed 3 rows containing missing values (`geom_segment()`).

#or
ggplot(weather_df, aes(x = tmax, y = name)) + 
  geom_density_ridges(scale = .85)
## Picking joint bandwidth of 1.54
## Warning: Removed 17 rows containing non-finite values
## (`stat_density_ridges()`).

learning assessment 2

ggplot(weather_df, aes(x = prcp)) + 
  geom_density(aes(fill = name), alpha = .5) 
## Warning: Removed 15 rows containing non-finite values (`stat_density()`).

ggplot(weather_df, aes(x = prcp, y = name)) + 
  geom_density_ridges(scale = .85)
## Picking joint bandwidth of 9.22
## Warning: Removed 15 rows containing non-finite values
## (`stat_density_ridges()`).

#box plot
ggplot(weather_df, aes(y = prcp, x = name)) + 
  geom_boxplot() 
## Warning: Removed 15 rows containing non-finite values (`stat_boxplot()`).

weather_df |> 
  filter(prcp > 0) |> 
  ggplot(aes(x = prcp, y = name)) + 
  geom_density_ridges(scale = .85)
## Picking joint bandwidth of 20.6

Saving and embedding plots

ggp_weather = 
  ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name), alpha = .5) 
ggsave("ggp_weather.pdf", ggp_weather, width = 8, height = 5)
## Warning: Removed 17 rows containing missing values (`geom_point()`).
knitr::opts_chunk$set(
  fig.width = 6,
  fig.asp = .6,
  out.width = "90%"
)
ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name))
## Warning: Removed 17 rows containing missing values (`geom_point()`).